Skip to content

Orchestra-Research/AI-Research-SKILLs / 18-multimodal/openpi

fine-tuning-serving-openpi

Verified

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.

references/config-recipes.md

View on GitHub
# Config Recipes

Use these as starting points when choosing a config to copy or adapt.

## Common config baselines

| Config | Typical use |
|--------|-------------|
| `pi05_libero` | Base pi0.5-style LIBERO fine-tuning recipe |
| `pi0_libero` | pi0 full fine-tuning on LIBERO-format data |
| `pi0_fast_libero` | pi0-fast full fine-tuning on LIBERO-format data |
| `pi0_aloha_pen_uncap` | ALOHA custom data fine-tuning pattern |
| `pi05_aloha_pen_uncap` | ALOHA pi0.5 custom data fine-tuning pattern |
| `pi05_droid_finetune` | Small custom DROID dataset in LeRobot format |
| `pi05_full_droid_finetune` | Full DROID RLDS large-scale training |
| `pi0_fast_full_droid_finetune` | Full DROID RLDS with pi0-fast |

## Essential command sequence

```bash
# 1) Compute normalization stats
uv run scripts/compute_norm_stats.py --config-name <config_name>

# 2) Train
XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 uv run scripts/train.py <config_name> \
  --exp-name=<run_name> --overwrite

# 3) Serve checkpoint for verification
uv run scripts/serve_policy.py policy:checkpoint \
  --policy.config=<config_name> \
  --policy.dir=checkpoints/<config_name>/<run_name>/<step>
```

## RLDS variant for full DROID

```bash
uv run --group rlds scripts/compute_norm_stats.py \
  --config-name pi05_full_droid_finetune --max-frames 10000000

XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 uv run --group rlds scripts/train.py \
  pi05_full_droid_finetune --exp-name=<run_name> --overwrite
```

## High-signal files to inspect while adapting configs

- `src/openpi/training/config.py` — all config definitions
- `src/openpi/policies/libero_policy.py` — LIBERO policy transforms
- `src/openpi/policies/droid_policy.py` — DROID policy transforms
- `src/openpi/policies/aloha_policy.py` — ALOHA policy transforms
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 323kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 323kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 323kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 323kUpdated Claude CodeCodexVerifiedInstall